# Audio Codec Enhancement with Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2001.09653 · HTML: https://mlsanity.com/paper/2001.09653/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2020.

## Built on by (most cited first, 12 of 12)

- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [FlowDec: A flow-based full-band general audio codec with high perceptual quality](https://mlsanity.com/paper/2503.01485/) (2025)
- [DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs](https://mlsanity.com/paper/2108.01216/) (2021)
- [Gull: A Generative Multifunctional Audio Codec](https://mlsanity.com/paper/2404.04947/) (2024)
- [VQCPC-GAN: Variable-Length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding](https://mlsanity.com/paper/2105.01531/) (2021)
- [NESC: Robust Neural End-2-End Speech Coding with GANs](https://mlsanity.com/paper/2207.03282/) (2022)
- [Neural Speech and Audio Coding: Modern AI Technology Meets Traditional Codecs](https://mlsanity.com/paper/2408.06954/) (2024)
- [TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network](https://mlsanity.com/paper/2505.18533/) (2025)
- [A DNN Based Post-Filter to Enhance the Quality of Coded Speech in MDCT Domain](https://mlsanity.com/paper/2201.12039/) (2022)
- [Enhanced Generative Machine Listener](https://mlsanity.com/paper/2509.21463/) (2025)
- [Utilizing Generative Adversarial Networks for Stable Structure Generation in Angry Birds](https://mlsanity.com/paper/2309.02614/) (2023)
- [Neural Spectral Band Generation for Audio Coding](https://mlsanity.com/paper/2506.06732/) (2025)

## Abstract (arXiv)

Audio codecs are typically transform-domain based and efficiently code stationary audio signals, but they struggle with speech and signals containing dense transient events such as applause. Specifically, with these two classes of signals as examples, we demonstrate a technique for restoring audio from coding noise based on generative adversarial networks (GAN). A primary advantage of the proposed GAN-based coded audio enhancer is that the method operates end-to-end directly on decoded audio samples, eliminating the need to design any manually-crafted frontend. Furthermore, the enhancement approach described in this paper can improve the sound quality of low-bit rate coded audio without any modifications to the existent standard-compliant encoders. Subjective tests illustrate that the proposed enhancer improves the quality of speech and difficult to code applause excerpts significantly.